Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    key objectives or purposes mentioned in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    锈钢
    -0.57
     Baillargeon
    -0.50
     Einf
    -0.48
    
    -0.48
     exce
    -0.48
    ÈRE
    -0.46
    ERON
    -0.46
    Solved
    -0.45
    mtx
    -0.45
     Dage
    -0.44
    POSITIVE LOGITS
     InputDecoration
    0.72
    HideFlags
    0.62
    ORIGINAL
    0.61
     raison
    0.60
     originais
    0.57
    ungguhnya
    0.57
    basicConfig
    0.56
    Original
    0.56
     intended
    0.54
     Original
    0.53
    Act Density 0.339%

    No Known Activations